import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Avrik/mirrors-edge-diffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Mirror's Edge Diffusion
A Stable Diffusion model trained on Mirror's Edge screenshots using Dreambooth.
Use the prompt MirrorsEdge style. Other notable tokens are abstract, floating shapes, cityscape, pristine, sterile, and back rooms.
If your outputs are too random and geometric, try adding abstract and floating shapes to the negative prompt.
- Downloads last month
- 41